Multi-font Script Identification Using Texture-Based Features

There are no files associated with this record.

Title Multi-font Script Identification Using Texture-Based Features
Author Busch, Andrew William
Publication Title Image Analysis and Recognition: Third International Conference, ICIAR 2006: Proceedings, Part 1
Editor Aurelio Campilho, Mohamed Kamel
Year Published 2006
Place of publication Berlin
Publisher Springer
Abstract The problem of determining the script and language of a document image has a number of important applications in the field of document analysis, such as indexing and sorting of large collections of such images, or as a precursor to optical character recognition (OCR). In this paper, we investigate the use of texture as a tool for determining the script of a document image, based on the observation that text has a distinct visual texture. An experimental evaluation of a number of commonly used texture features is conducted on a newly created script database, providing a qualitative measure of which features are most appropriate for this task. Strategies for improving classification results in situations with limited training data and multiple font types are also proposed.
Peer Reviewed Yes
Published Yes
Publisher URI
ISBN 3-540-44891-8
Conference name Third International Confernece on Image Analysis and Recognition (ICIAR 2006)
Location Povoa de Varzim, Portugal
Date From 2006-09-18
Date To 2006-09-20
Date Accessioned 2007-03-16
Language en_AU
Faculty Faculty of Science, Environment, Engineering and Technology
Subject PRE2009-Image Processing
Publication Type Conference Publications (Full Written Paper - Refereed)
Publication Type Code e1

Show simple item record

Griffith University copyright notice